Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words related to physical bones and skeletal structures

    oai_token-act-pair · gpt-3.5-turbo

    references to skeletal structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    VT
    -0.72
    OP
    -0.67
     ECO
    -0.66
    Effective
    -0.65
     authorized
    -0.64
    EC
    -0.62
     Directive
    -0.62
    opt
    -0.62
    VW
    -0.61
     Anonymous
    -0.61
    POSITIVE LOGITS
     bones
    3.92
    bones
    2.73
     bone
    2.34
    bone
    2.17
     Bones
    2.00
     skeletons
    1.99
     skulls
    1.89
    Bone
    1.78
     ribs
    1.78
     skeleton
    1.74
    Act Density 0.017%

    No Known Activations